Saturday March 23, 2019
Home Lead Story Now Machine L...

Now Machine Learning Can Help in Predicting Earthquakes

The techniques can also be used to better identify earthquake aftershocks, volcanic seismic activity, monitor tectonic tremor, locate earthquake's origin and distinguish small earthquakes from other seismic "noise"

0
//
Indian Seismologist succesfully preditcs several earthquakes beforehand by studying data,.
Earthquake prediction enables emergency measures to reduce death and destruction. Pixabay

Besides applications on problems like digital image and speech recognition, machine learning (ML) methods are also used to predict complicated patterns in earthquake activity, say researchers.

It can be used to hone predictions of seismic activity, identify earthquake centres, characterise different types of seismic waves and distinguish seismic activity from other kinds of ground “noise”, according to a team of seismologists.

More seismologists are using the method, driven by “the increasing size of seismic data sets, improvements in computational power, new algorithms and architecture and the availability of easy-to-use open source machine learning frameworks,” said the team, including Karianne Bergen from the Harvard University in the USA, in a paper published in the journal Seismological Research Letters.

los angeles, earthquake, ShakeAlertLa
A mobile phone customer looks at an earthquake warning application on their phone in Los Angeles, Jan. 3, 2019. The app, called ShakeAlertLA, is available for download on Android and Apple phones. VOA

These methods, called deep neural networks, can explore the complex relationships between input data and their predicted output. For instance, one kind of deep neural network can be used to develop ground motion models for natural and induced earthquakes in Oklahoma, Kansas and Texas.

The unusual nature of the growing number of earthquakes caused by petroleum wastewater disposal in the region makes it essential to predict ground motion for future earthquakes and to possibly mitigate their impact, the researchers noted.

Also Read- North Korean Hackers Behind Surge in Cyberattacks on Banks: Report

The techniques can also be used to better identify earthquake aftershocks, volcanic seismic activity, monitor tectonic tremor, locate earthquake’s origin and distinguish small earthquakes from other seismic “noise”, they said. (IANS)

Next Story

Microsoft Opens its Machine Learning Framework For All

Infer.NET was used to publish hundreds of research papers using a variety of fields, everything from information retrieval to healthcare

0
Microsoft
Microsoft launches e-commerce portal for Telangana's handloom weavers. Pixabay

Global tech giant Microsoft has opened its cross-platform frameworks Infer.NET — a machine learning engine used in Office, Xbox and Azure — for one and all worldwide.

“We’re extremely excited today to open source Infer.NET on GitHub under the permissive MIT license for free use in commercial applications,” Yordan Zaykov, Principal Research Software Engineering Lead at Microsoft, wrote in a blog post on Friday.

Developed in 2014 by Microsoft’s research lab in Cambridge, Infer.NET was initially envisioned as a research tool and later in 2008 was released for academic use.

Infer.NET enables a model-based approach to machine learning. It lets users incorporate domain knowledge into their model.

The framework can then build a bespoke machine learning algorithm directly from that model.

Microsoft
A sign for Microsoft is seen on a building in Cambridge. VOA

“This means that instead of having to map your problem onto a pre-existing learning algorithm that you’ve been given, Infer.NET actually constructs a learning algorithm for you, based on the model you’ve provided,” Zaykov said.

He noted that the Infer.NET team is looking forward to engaging with the open-source community in developing. Infer.NET will become a part of ML.NET — the machine learning framework for .NET developers.

“We have already taken several steps towards integration with ML.NET, like setting up the repository under the .NET Foundation and moving the package and namespaces to Microsoft.ML.Probabilistic. Infer.NET will extend ML.NET for statistical modelling and online learning,” Zaykov said.

Also Read- India-Russia Sign An Air Defense System Deal

Infer.NET was used to publish hundreds of research papers using a variety of fields, everything from information retrieval to healthcare.

In 2012 Infer.NET even won a Patents for Humanity award for aiding research in epidemiology, genetic causes of disease, deforestation and asthma. (IANS)